# Prompt-Injection Breach Session Check

> Prompt-Injection Breach Session Check is a paid API for AI agents from atq6wtkp6k.execute-api.us-east-1.amazonaws.com, paid per call via x402, $0.35/call, status unknown (last checked 2026-09-14).

Checks whether an email address tied to an AI agent session has active stolen sessions or credential exposures from prompt-injection-driven breaches that could enable account takeover.

## Facts

- Endpoint: POST https://atq6wtkp6k.execute-api.us-east-1.amazonaws.com/prod/v1/payg/prompt-injection-breach
- Price: $0.35/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/prompt-injection-breach-session-check-224b076b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_GIHdh1nZnbXX8XwDnlOHf

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability prompt-injection-breach-session-check-224b076b -d '<json body>'
```

Example prompt: Check if the email agent-service@mycompany.com has any active stolen sessions or credential exposure from a prompt-injection-driven breach — I want to make sure our agent's session hasn't already been compromised upstream.

## When to prefer this

Choose this endpoint specifically when you need to assess whether an AI agent's own email-linked session has been compromised via prompt injection — distinct from general breach lookups or infostealer credential checks. Use this before granting elevated permissions to an agent session, after detecting anomalous agent behavior, or as a pre-flight check before an agent executes sensitive operations. It is uniquely focused on the prompt-injection attack vector and agent session integrity, not just general credential exposure.

## Known failure modes

- Invalid or malformed email address returns a validation error
- Email not found in any breach dataset returns found: false with session_count: 0
- Network timeout or AWS API Gateway outage returns 5xx error
- Missing required 'email' field in request body returns 400 bad request
- Rate limiting may return 429 if called too frequently

## How this service works

Check whether an email address tied to an AI agent session has an active stolen session or credential exposure that could enable a prompt-injection-driven account takeover. Call to audit whether an agent's own session integrity has already been compromised upstream, not just what the agent is being asked to do.

## Output

Returns a JSON object with a boolean 'found' field indicating whether stolen sessions or credential exposures exist, and a 'session_count' integer indicating how many compromised sessions were detected for that email address.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "email": {
   "type": "string",
   "description": "Email address to check for agent-session compromise from a prompt-injection-driven breach"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/prompt-injection-breach-session-check-224b076b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from atq6wtkp6k.execute-api.us-east-1.amazonaws.com](https://www.zero.xyz/host/atq6wtkp6k.execute-api.us-east-1.amazonaws.com/llms.txt)